This paper describes several approaches to the automatic rating of the concreteness of concepts in context, to approach the EVALITA 2020 “CONcre-TEXT” task. Our systems focus on the interplay between words and their surrounding context by (i) exploiting annotated re-sources, (ii) using BERT masking to find potential substitutes of the target in specific contexts and measuring their average similarity with concrete and abstract centroids, and (iii) automatically generating labelled datasets to fine tune transformer models for regression. All the approaches have been tested both on English and Italian data. Both the best systems for each language ranked second in the task.

CAPISCO@CONcreTEXT 2020: (Un)supervised Systems to Contextualize Concreteness with Norming Data

Alessandro Bondielli
Primo
;
Lucia Passaro
Penultimo
;
Alessandro Lenci
Ultimo
2020

Abstract

This paper describes several approaches to the automatic rating of the concreteness of concepts in context, to approach the EVALITA 2020 “CONcre-TEXT” task. Our systems focus on the interplay between words and their surrounding context by (i) exploiting annotated re-sources, (ii) using BERT masking to find potential substitutes of the target in specific contexts and measuring their average similarity with concrete and abstract centroids, and (iii) automatically generating labelled datasets to fine tune transformer models for regression. All the approaches have been tested both on English and Italian data. Both the best systems for each language ranked second in the task.
9791280136275
File in questo prodotto:
File Dimensione Formato  
Bondielli_etal_CAPISCO.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: Versione finale editoriale
Licenza: Creative commons
Dimensione 353.67 kB
Formato Adobe PDF
353.67 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11568/1069968
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact